CSCI-6100

Machine and Computational Learning

Introduction to the theory, algorithms, and applications of automated learning (supervised, reinforcement, and unsupervised), how much information and computation are needed to learn a task, and how to accomplish it. Emphasis will be given to unifying approaches coming from statistics, function approximation, optimization, and pattern recognition. Topics include: Decision Trees, Neural Networks, RBF’s, Bayesian Learning, PAC Learning, Support Vector Machines, Gaussian processes, Hidden Markov Models. Prerequisites: familiarity with probability, linear algebra, and calculus. Offered on availability of instructor.

3 credit hours